Searching...
12 results for “system reliability”
metric, you have a good visibility to how's the application and some models are performing. It might do something very dumb or it can cause you, like I know. Some something like crazy can happen. So so yeah. So so so I do think eval is very, very imp
26:13 / 27:16
from transcript26:13 – 27:16
...main reason is reliability. And, again, the term hallucination may be not the best terms, but these are probabilistic machines, and, they're for sometimes often, they'll give you brilliant output. But if you're brilliant 95% of the time, not just wro
3:04 / 4:04
from transcript3:04 – 4:04
...reliability better. And so it's we actually again, knock on wood. We're we think we've got reliability in the spot where we're, like, comfortable kind of putting this out there, and and kind of, like, letting people actually see their their SLO. And,
42:44 / 43:50
from transcript42:44 – 43:50
liking the answer, you can actually give a thumbs up. Or if you don't like the answer, sometimes customers don't give you thumbs down, but actually re regenerate the answer. So that is a clear indication that the initial answer that you generated is
35:15 / 36:25
from transcript35:15 – 36:25
...systems in the context of site reliability engineering appeals to very large enterprises, but at the same time, we wanna make sure that the same technology is helping mid market as well. So, essentially, I should think about SREs as very, very specia
11:10 / 12:56
from transcript11:10 – 12:56
“Stripe achieved 99.99986% API uptime - just 44 seconds down all year”
a lot of, you know, infrastructure in order to make, MongoDB as fault tolerant and as distributed and as Mhmm. Durable and as reliable and everything as we needed it to be and as it now is. Like we ha
23:23 / 24:05
tactical advice23:23 – 24:05
...before going to a point of complete, autonomy. And the second thing is you're also kind of, building this, you know, implicit logging system. A lot of people come and tell us that, oh, wait. There are emails. Right? Why do you need something like thi
55:23 / 56:32
from transcript55:23 – 56:32
...a system prompt that is the user simulator. And we do that, but it's, like, okay. But, like, the breadth of ways a user might respond, there's, like, a lot more diversity in that than the actual diversity you'll get in practice when you have this, li
24:42 / 26:13
from transcript24:42 – 26:13
...systems in the context of site reliability engineering appeals to very large enterprises, but at the same time, we wanna make sure that the same technology is helping mid market as well. So, essentially, I should think about SREs as very, very specia
11:59 / 13:04
from transcript11:59 – 13:04
...system does. That's and and in many different ways. And, so let's say you're Airbnb. Right? And I'm bringing this up because this is an example of one that, like, you know, companies have gone out and built sandboxes. Like, if you're Airbnb and you'r
24:02 / 25:05
from transcript24:02 – 25:05
...systems in a very old school way. Like like a morbid analogy is you have a bunch of sensors detecting a nuclear strike. How do you make sure that they act correctly? Is you need a high degree of independent verifiable sensors that is necessary to cor
30:45 / 31:50
from transcript30:45 – 31:50
“Why traditional software only automates things that are easy to explain”
The slide is that traditional software is deterministic and does things that are easy to explain to machines. In fact, automation, machine tools, sewing machines, typewriters, adding machines Right. T
18:05 / 18:30
framework18:05 – 18:30
Have a podcast?
Run your podcast through Clypt
Get ranked clips, hooks, and ready-to-post copy from your own episodes. Free to try.